# Your Data, My Model: Learning Who Really Helps in Federated Learning

arXiv: https://arxiv.org/abs/2409.02064 · HTML: https://mlsanity.com/paper/2409.02064/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 27 references that are in the map.
- First posted on arXiv 3 Sep 2024.

## Builds on (most cited first, 11 of 11)

- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Federated Multi-Task Learning](https://mlsanity.com/paper/1705.10467/) (2017)
- [An Efficient Framework for Clustered Federated Learning](https://mlsanity.com/paper/2006.04088/) (2020)
- [Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraints](https://mlsanity.com/paper/1910.01991/) (2019)
- [Network Lasso: Clustering and Optimization in Large Graphs](https://mlsanity.com/paper/1507.00280/) (2015)
- [Personalized Federated Learning under Mixture of Distributions](https://mlsanity.com/paper/2305.01068/) (2023)
- [Confidence-aware Personalized Federated Learning via Variational Expectation Maximization](https://mlsanity.com/paper/2305.12557/) (2023)
- [Provably Personalized and Robust Federated Learning](https://mlsanity.com/paper/2306.08393/) (2023)
- [FedHB: Hierarchical Bayesian Federated Learning](https://mlsanity.com/paper/2305.04979/) (2023)
- [Clustered Federated Learning via Generalized Total Variation Minimization](https://mlsanity.com/paper/2105.12769/) (2021)
- [Low-Regret Active learning](https://mlsanity.com/paper/2104.02822/) (2021)

## Abstract (arXiv)

Many important machine learning applications involve networks of devices-such as wearables or smartphones-that generate local data and train personalized models. A key challenge is determining which peers are most beneficial for collaboration. We propose a simple and privacy-preserving method to select relevant collaborators by evaluating how much a model improves after a single gradient step using another devices data-without sharing raw data. This method naturally extends to non-parametric models by replacing the gradient step with a non-parametric generalization. Our approach enables model-agnostic, data-driven peer selection for personalized federated learning (PersFL).